Upload 6 files
Browse files- config (1).json +77 -0
- feature_extractor_config.json +8 -0
- preprocessor_config (1).json +8 -0
- special_tokens_map (1).json +1 -0
- tokenizer_config (1).json +1 -0
- vocab (1).json +1 -0
config (1).json
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base-960h",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"apply_spec_augment": true,
|
5 |
+
"architectures": [
|
6 |
+
"Wav2Vec2ForCTC"
|
7 |
+
],
|
8 |
+
"attention_dropout": 0.1,
|
9 |
+
"bos_token_id": 1,
|
10 |
+
"codevector_dim": 256,
|
11 |
+
"contrastive_logits_temperature": 0.1,
|
12 |
+
"conv_bias": false,
|
13 |
+
"conv_dim": [
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512
|
21 |
+
],
|
22 |
+
"conv_kernel": [
|
23 |
+
10,
|
24 |
+
3,
|
25 |
+
3,
|
26 |
+
3,
|
27 |
+
3,
|
28 |
+
2,
|
29 |
+
2
|
30 |
+
],
|
31 |
+
"conv_stride": [
|
32 |
+
5,
|
33 |
+
2,
|
34 |
+
2,
|
35 |
+
2,
|
36 |
+
2,
|
37 |
+
2,
|
38 |
+
2
|
39 |
+
],
|
40 |
+
"ctc_loss_reduction": "sum",
|
41 |
+
"ctc_zero_infinity": false,
|
42 |
+
"diversity_loss_weight": 0.1,
|
43 |
+
"do_stable_layer_norm": false,
|
44 |
+
"eos_token_id": 2,
|
45 |
+
"feat_extract_activation": "gelu",
|
46 |
+
"feat_extract_dropout": 0.0,
|
47 |
+
"feat_extract_norm": "group",
|
48 |
+
"feat_proj_dropout": 0.1,
|
49 |
+
"feat_quantizer_dropout": 0.0,
|
50 |
+
"final_dropout": 0.1,
|
51 |
+
"gradient_checkpointing": false,
|
52 |
+
"hidden_act": "gelu",
|
53 |
+
"hidden_dropout": 0.1,
|
54 |
+
"hidden_dropout_prob": 0.1,
|
55 |
+
"hidden_size": 768,
|
56 |
+
"initializer_range": 0.02,
|
57 |
+
"intermediate_size": 3072,
|
58 |
+
"layer_norm_eps": 1e-05,
|
59 |
+
"layerdrop": 0.1,
|
60 |
+
"mask_feature_length": 10,
|
61 |
+
"mask_feature_prob": 0.0,
|
62 |
+
"mask_time_length": 10,
|
63 |
+
"mask_time_prob": 0.05,
|
64 |
+
"model_type": "wav2vec2",
|
65 |
+
"num_attention_heads": 12,
|
66 |
+
"num_codevector_groups": 2,
|
67 |
+
"num_codevectors_per_group": 320,
|
68 |
+
"num_conv_pos_embedding_groups": 16,
|
69 |
+
"num_conv_pos_embeddings": 128,
|
70 |
+
"num_feat_extract_layers": 7,
|
71 |
+
"num_hidden_layers": 12,
|
72 |
+
"num_negatives": 100,
|
73 |
+
"pad_token_id": 0,
|
74 |
+
"proj_codevector_dim": 256,
|
75 |
+
"transformers_version": "4.7.0.dev0",
|
76 |
+
"vocab_size": 32
|
77 |
+
}
|
feature_extractor_config.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_dim": 1,
|
4 |
+
"padding_side": "right",
|
5 |
+
"padding_value": 0.0,
|
6 |
+
"return_attention_mask": false,
|
7 |
+
"sampling_rate": 16000
|
8 |
+
}
|
preprocessor_config (1).json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"do_normalize": true,
|
3 |
+
"feature_size": 1,
|
4 |
+
"padding_side": "right",
|
5 |
+
"padding_value": 0.0,
|
6 |
+
"return_attention_mask": false,
|
7 |
+
"sampling_rate": 16000
|
8 |
+
}
|
special_tokens_map (1).json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
|
tokenizer_config (1).json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "return_attention_mask": false, "do_normalize": true}
|
vocab (1).json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}
|